Home / Current Issue / Paper 1718631
Evolutionary Computation-Enhanced White-Box Penetration Testing for Lateral-Movement Prevention in Zero-Trust Architectures
Subject area: Science,Engineering and Technology · Area of research: Sciences
Abstract
Preventing lateral movement remains a central cybersecurity challenge even in environments designed according to Zero Trust principles. Although this paradigm reduces implicit trust and enforces continuous verification, its effectiveness ultimately depends on access-policy quality, identity-to-resource segmentation, and the ability to detect abusive chains built from seemingly legitimate permissions. In parallel, recent automated penetration-testing research has advanced through reinforcement learning, graph-based modeling, and simulation frameworks for exploring complex attack surfaces [1-4]. Building on this state of the art, this article proposes a conceptual white-box penetration-testing framework for Zero-Trust architectures in which evolutionary algorithms perform global search over the internal blueprint of the environment, while reinforcement learning adaptively refines promising action sequences. The model assumes authorized defensive access to ZTNA policies, identity and privilege graphs, workload dependencies, and continuous-verification logs. Its fitness function is multi-objective and jointly considers success probability, stealth, and evasion rate. We argue that this combination may improve the identification of plausible lateral-movement routes and generate more useful remediation outputs, provided that it is applied in controlled environments with telemetry sufficiently faithful to the real system.
Keywords
Automated Penetration Testing, Evolutionary Computation, Reinforcement Learning, Lateral Movement, Zero Trust.
References
[1] Moreno AC, Hernandez-Suarez A, Sanchez-Perez G, Toscano-Medina LK, Perez-Meana H, Portillo-Portillo J, Olivares-Mercado J, García Villalba LJ. Analysis of Autonomous Penetration Testing Through Reinforcement Learning and Recommender Systems. Sensors (Basel). 2025;25(1):211.
[2] Lei H, Ge Y, Zhu Q. ADAPT: A Game-Theoretic and Neuro-Symbolic Framework for Automated Distributed Adaptive Penetration Testing. arXiv [Preprint]. 2024:2411.00217.
[3] Wang Y, Liu S, Wang W, Zhou C, Zhang C, Jin J, Zhu C. A Unified Modeling Framework for Automated Penetration Testing. Comput Secur. 2026;162:104787.
[4] Chen Z, Kang F, Xiong X, Shu H. A Survey on Penetration Path Planning in Automated Penetration Testing. Appl Sci. 2024;14(18):8355.
[5] Ghanem MC, Chen TM. Reinforcement Learning for Intelligent Penetration Testing. In: 2018 World Conference on Smart Trends in Systems, Security and Sustainability. 2018. p. 185-192.
[6] Janisch J, Pevný T, Lisý V. NASimEmu: Network Attack Simulator & Emulator for Training Agents Generalizing to Novel Scenarios. In: Machine Learning and Knowledge Discovery in Databases. Cham: Springer; 2023. p. 565-582.
[7] Li Y, Dai H, Yan J. Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine. In: 2024 International Joint Conference on Neural Networks. 2024.
[8] Becker N, Reti D, Ntagiou EV, Wallum M, Schotten HD. Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN. arXiv [Preprint]. 2024:2407.15656.
[9] Bowman B, Laprade C, Ji Y, Huang HH. Detecting Lateral Movement in Enterprise Computer Networks with Unsupervised Graph AI. In: Recent Advances in Intrusion Detection. Cham: Springer; 2020. p. 257-268.
[10] King IJ, Huang HH. Euler: Detecting Network Lateral Movement via Scalable Temporal Link Prediction. ACM Trans Priv Secur. 2023;26(3):1-30.
[11] Khoury J, Klisura D, Zand H, De La Torre Parra G, Najafirad P, Bou-Harb E. Jbeil: Temporal Graph-Based Inductive Learning to Infer Lateral Movement in Evolving Enterprise Networks. In: 2024 IEEE Symposium on Security and Privacy. 2024. p. 3644-3660.
[12] Gambo ML, Almulhem A. Zero Trust Architecture: A Systematic Literature Review. J Netw Syst Manage. 2026;34(1):25.
[13] Ge Y, Zhu Q. GAZETA: GAme-Theoretic ZEro-Trust Authentication for Defense Against Lateral Movement in 5G IoT Networks. IEEE Trans Inf Forensics Secur. 2024;19:540-554.
[14] Sedjelmaci H, Ansari N. Zero Trust Architecture Empowered Attack Detection Framework to Secure 6G Edge Computing. IEEE Netw. 2024;38(1):196-202.
[15] Alhomidi MA, Reed MJ. A Genetic Algorithm Approach for the Most Likely Attack Path Problem. In: 2013 International Conference on Availability, Reliability and Security. 2013.
[16] Khouzani MHR, Liu Z, Malacaria P. Scalable min-max multi-objective cyber-security optimisation over probabilistic attack graphs. Eur J Oper Res. 2019;278(3):894-903.
[17] Pourre, C. B. F. (2024). UMA ANÁLISE BIBLIOMÉTRICA DA PESQUISA DE FRAMEWORK DE CIDADES INTELIGENTES. Revista Sistemática, 14(8), 591–605. https://doi.org/10.56238/rcsv14n8-00926.
[18] [1:19 PM, 19/05/2026] Carlla Furlan Pourre: POURRE, C. B. F. Indicadores de resultados finalísticos como instrumento de diagnóstico do transporte urbano: um estudo de caso do Distrito Federal. 2020. Dissertação (Mestrado em Arquitetura e Urbanismo) – Universidade Federal de Brasília, Brasília, 2020. Disponível em: https://repositorio.unb.br/handle/10482/38743. Acesso em: 23 out. 2025.
[19] Carlla Furlan Pourre: FURLAN, Carlla Brito; SANTOS, Gleys Ially Ramos dos. 2016. A qualidade do transporte público urbano em cidades médias: estudo de caso em Palmas-Tocantins. Revista em Gestão, Inovação e Sustentabilidade. Disponível em: chrome-extension://efaidnbmnnMarecilda; Mello, Cristina de. 2022.
[20] Gotardi Pessoa, E. (2025). Analysis of the performance of helical piles under various load and geometry conditions. ITEGAM-JETIA, 11(53), 135-140. https://doi.org/10.5935/jetia.v11i53.1887
[21] Gotardi Pessoa, E. (2025). Sustainable solutions for urban infrastructure: The environmental and economic benefits of using recycled construction and demolition waste in permeable pavements. ITEGAM-JETIA, 11(53), 131-134. https://doi.org/10.5935/jetia.v11i53.1886
How to cite this paper
@article{1718631,
author = {Valdir de Espíndula},
title = {Evolutionary Computation-Enhanced White-Box Penetration Testing for Lateral-Movement Prevention in Zero-Trust Architectures},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {2643-2647},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718631.pdf},
abstract = {Preventing lateral movement remains a central cybersecurity challenge even in environments designed according to Zero Trust principles. Although this paradigm reduces implicit trust and enforces continuous verification, its effectiveness ultimately depends on access-policy quality, identity-to-resource segmentation, and the ability to detect abusive chains built from seemingly legitimate permissions. In parallel, recent automated penetration-testing research has advanced through reinforcement learning, graph-based modeling, and simulation frameworks for exploring complex attack surfaces [1-4]. Building on this state of the art, this article proposes a conceptual white-box penetration-testing framework for Zero-Trust architectures in which evolutionary algorithms perform global search over the internal blueprint of the environment, while reinforcement learning adaptively refines promising action sequences. The model assumes authorized defensive access to ZTNA policies, identity and privilege graphs, workload dependencies, and continuous-verification logs. Its fitness function is multi-objective and jointly considers success probability, stealth, and evasion rate. We argue that this combination may improve the identification of plausible lateral-movement routes and generate more useful remediation outputs, provided that it is applied in controlled environments with telemetry sufficiently faithful to the real system.},
keywords = {Automated Penetration Testing, Evolutionary Computation, Reinforcement Learning, Lateral Movement, Zero Trust.},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1718631}
}